[fix] fix for prior preservation and mixed precision sampling

[Brvcket]

There were 4 issues fixed:

1. When sampling with prior preservation, the prompt was not passed to the correct argument position, causing a generation error during sampling.
2. When sampling with prior preservation, the transformer passed to the pipeline did not have the torch_dtype argument, causing issues with mixed precision.
3. When sampling with prior preservation, the prompt was passed in fp32 without proper casting, leading to mixed precision mismatches.
4. When not args.train_text_encoder, prompt_embeds and pooled_prompt_embeds were None, leading to the same error as reported in RuntimeError: The size of tensor a (4608) must match the size of tensor b (5120) at non-singleton dimension 2 during DreamBooth Training with Prior Preservation #10722.

[Brvcket]

@linoytsaban Am I correct in assuming that your review is required? I'm sorry if I tagged the wrong person

[linoytsaban]

thanks @Brvcket!

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[sayakpaul]

Thanks a lot!